{"id":"https://openalex.org/W4408352258","doi":"https://doi.org/10.1109/icassp49660.2025.10890132","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","display_name":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352258","doi":"https://doi.org/10.1109/icassp49660.2025.10890132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413319","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0002-6016-5582"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050682332","display_name":"Chenxing Li","orcid":"https://orcid.org/0000-0002-3997-8212"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086097247","display_name":"Manjie Xu","orcid":"https://orcid.org/0000-0001-9220-3662"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Manjie Xu","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017750410","display_name":"Wei Liang","orcid":"https://orcid.org/0000-0002-4679-9693"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352646","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-6939-0850"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049346285","display_name":"Rilin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rilin Chen","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101416140","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0001-6089-4905"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]},{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Seattle,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Seattle,USA","institution_ids":["https://openalex.org/I70745867","https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966454029083252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43081721663475037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.370268315076828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966454029083252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43081721663475037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.370268315076828}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2964218959","https://openalex.org/W3015371781","https://openalex.org/W3113172960","https://openalex.org/W3169483174","https://openalex.org/W4213286388","https://openalex.org/W4372260310","https://openalex.org/W4372348103","https://openalex.org/W4386075767","https://openalex.org/W4387969125","https://openalex.org/W4390873054","https://openalex.org/W4392427699","https://openalex.org/W4392910528","https://openalex.org/W4393147998","https://openalex.org/W4396877837","https://openalex.org/W4402112400","https://openalex.org/W4402727849","https://openalex.org/W4403780823","https://openalex.org/W4403791730","https://openalex.org/W4404545746","https://openalex.org/W4411245083","https://openalex.org/W6640963894","https://openalex.org/W6783867762","https://openalex.org/W6840815571","https://openalex.org/W6849109464","https://openalex.org/W6853285550","https://openalex.org/W6854445938","https://openalex.org/W6859740657","https://openalex.org/W6862315687","https://openalex.org/W6868818234","https://openalex.org/W6869264470","https://openalex.org/W6869582388","https://openalex.org/W6870515680"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Visual":[0],"and":[1,41,59,64,96,124,140,159],"auditory":[2],"perception":[3],"are":[4,173],"two":[5],"crucial":[6],"ways":[7],"humans":[8],"experience":[9],"the":[10,19,23,77,108,166],"world.":[11],"Text-to-video":[12],"generation":[13,51],"has":[14],"made":[15],"remarkable":[16],"progress":[17],"over":[18],"past":[20],"year,":[21],"but":[22],"absence":[24],"of":[25,79,168],"harmonious":[26],"audio":[27,50,153],"in":[28,82,112,151],"generated":[29],"video":[30,62,68],"limits":[31],"its":[32],"broader":[33],"applications.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,84,114],"propose":[39,85,115],"Semantic":[40],"Temporal":[42],"Aligned":[43],"Video-to-Audio":[44,149],"(STA-V2A),":[45],"an":[46,86,97],"approach":[47],"that":[48,144],"enhances":[49],"from":[52],"videos":[53],"by":[54],"extracting":[55],"both":[56],"local":[57,92],"temporal":[58,93,160],"global":[60,102],"semantic":[61,103,110,157],"features":[63,69],"combining":[65],"these":[66],"refined":[67],"with":[70,120,154],"text":[71],"as":[72],"cross-modal":[73,125],"guidance.":[74,126],"To":[75,106],"address":[76],"issue":[78],"information":[80,111],"redundancy":[81],"videos,":[83,113],"onset":[87],"prediction":[88],"pretext":[89],"task":[90],"for":[91,101],"feature":[94,104],"extraction":[95],"attentive":[98],"pooling":[99],"module":[100],"extraction.":[105],"supplement":[107],"insufficient":[109],"a":[116,132],"Latent":[117],"Diffusion":[118],"Model":[119],"Text-to-Audio":[121],"priors":[122],"initialization":[123],"We":[127],"also":[128],"introduce":[129],"Audio-Audio":[130],"Align,":[131],"new":[133],"metric":[134],"to":[135],"assess":[136],"audio-temporal":[137],"alignment.":[138,161],"Subjective":[139],"objective":[141],"metrics":[142],"demonstrate":[143],"our":[145],"method":[146],"surpasses":[147],"existing":[148],"models":[150],"generating":[152],"better":[155],"quality,":[156],"consistency,":[158],"The":[162],"ablation":[163],"experiment":[164],"validated":[165],"effectiveness":[167],"each":[169],"module.":[170],"Audio":[171],"samples":[172],"available":[174],"at":[175],"https://y-ren16.github.io/STAV2A.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}